Skip to content

Sb3NetworkArchitectureArgs

Full path: schola.scripts.sb3.settings.Sb3NetworkArchitectureArgs

schola.scripts.sb3.settings.Sb3NetworkArchitectureArgs

Sb3NetworkArchitectureArgs

Sb3NetworkArchitectureArgs(policy_parameters: 'Annotated[List[int], Parameter(consume_multiple=True)]' = <factory>, critic_parameters: 'Annotated[List[int], Parameter(consume_multiple=True)]' = <factory>, activation: 'ActivationFunctionEnum' = <ActivationFunctionEnum.ReLU: 'relu'>)

Bases: object

Methods

ItemDescription
init

Attributes

ItemDescription
activationActivation function to use in the policy and critic networks.
policy_parametersA list of layer widths representing the policy network architecture.
critic_parametersA list of layer widths representing the critic (value function) network architecture.

Parameters

policy_parameters (Annotated[List[int], Parameter(consume_multiple=True)])

critic_parameters (Annotated[List[int], Parameter(consume_multiple=True)])

activation (ActivationFunctionEnum)

init

__init__(policy_parameters=<factory>, critic_parameters=<factory>, activation=ActivationFunctionEnum.ReLU)

Parameters

policy_parameters (Annotated[List[int], Parameter(consume_multiple=True)])

critic_parameters (Annotated[List[int], Parameter(consume_multiple=True)])

activation (ActivationFunctionEnum)

Returns

None


activation

= 'relu' activation: ActivationFunctionEnum

Activation function to use in the policy and critic networks. This determines the non-linear activation function applied to each layer of the neural networks. The choice of activation function can affect the performance of the model and may depend on the specific characteristics of the environment.


critic_parameters

critic_parameters: Annotated[List[int], Parameter(consume_multiple=True)]

A list of layer widths representing the critic (value function) network architecture. This defines the number of neurons in each hidden layer of the critic network. For example, [64, 64] would create a critic network with two hidden layers, each containing 64 neurons. This is only applicable for algorithms that use a critic (e.g., SAC). If set to None, it will use the default architecture defined by the algorithm.


policy_parameters

policy_parameters: Annotated[List[int], Parameter(consume_multiple=True)]

A list of layer widths representing the policy network architecture. This defines the number of neurons in each hidden layer of the policy network. For example, [64, 64] would create a policy network with two hidden layers, each containing 64 neurons. If set to None, it will use the default architecture defined by the algorithm.